Disturbance Removal Device for Distance Sensor False Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing interference prevention devices with distance measurement sensors erroneously detect granular disturbance objects like raindrops or snow particles as work machines or people, leading to unnecessary warnings and interruptions in construction operations.

Innovation Solution

A disturbance removal device that uses distance measurement sensors to extract candidate pixels from distance images, calculates feature values indicating temporal changes, and removes pixels with excessive velocity, angle, or acceleration to distinguish and eliminate disturbance objects, ensuring accurate detection of target objects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a distance measurement sensor is used to detect work machines and people, then interference prevention capability is improved, but false detection of disturbance objects (raindrops, snow particles) increases

Engineering Contradiction:
Improveinterference prevention capabilityVSAvoiddetection accuracy
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent applies dynamics by utilizing the temporal变化 characteristics of detected objects. Disturbance objects like raindrops and snow particles exhibit different movement patterns (velocity, acceleration, trajectory changes) compared to work machines and people. The system dynamically analyzes these temporal characteristics across multiple measurement time points to distinguish between true targets and disturbance objects, thereby maintaining high detection accuracy while preventing false alarms.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the detection parameters from static distance measurement to dynamic multi-parameter analysis. By measuring not only distance but also velocity, acceleration, and trajectory changes over time, the system creates a multi-dimensional parameter space for object characterization. This parameter transformation enables the differentiation of disturbance objects from legitimate targets based on their distinct motion signatures.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If disturbance objects are removed from distance images, then false detection is reduced, but operational complexity increases

Engineering Contradiction:
Improvedetection accuracyVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the detection process into distinct functional modules: a measurement unit for acquiring distance data, a calculation unit for computing temporal characteristics (velocity, acceleration), and a removal unit for eliminating disturbance objects. This segmentation allows each module to perform its specific function efficiently, reducing overall system complexity while achieving accurate disturbance object removal.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs self-service by automatically calculating temporal characteristics and identifying disturbance objects without requiring manual intervention. The removal unit autonomously determines which detected objects are disturbance objects based on their motion characteristics and removes them from the distance image, enabling the system to self-correct detection errors in real-time.

Inventive Principle:
Principle #25Self-service

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Effectively prevents false detection of disturbance objects, reducing unnecessary warnings and operational interruptions by accurately removing granular objects from distance images while maintaining target object detection, thus enhancing operational safety and efficiency.

Implementation Method 1

a distance measurement sensor that chronologically acquires a plurality of distance images indicating a distance distribution of a surrounding environment

Methodology Applied
Scientific EffectTime of flight: Time of Flight

Data Source

PatentEP3416129B1External interference removal device
Publication Date: 2022.04.06 KOBE STEEL LTD
  • EP3416129B1 patent drawingFigure 1
  • EP3416129B1 patent drawingFigure 2
  • EP3416129B1 patent drawingFigure 3

AI summary

An extraction unit (151) extracts, as a candidate pixel of a disturbance object, a predetermined number of pixels in order of smaller distance from each distance image acquired by a distance measurement sensor (16), the predetermined number being one or more. A calculation unit (152) calculates a feature value indicating a characteristic of temporal change between each candidate pixel in a distance image of a current frame and a corresponding candidate pixel in a distance image of a past frame. A removal unit (153) specifies, as a pixel indicating a disturbance object, a candidate pixel the feature value of which calculated by the calculation unit (152) is larger than a predetermined reference feature value, and removes the specified pixel from the distance image of the current frame.